Stability AI releases DeepFloyd IF, a powerful text-to-image model

Re:Stability AI releases DeepFloyd IF, a powerful text-to-im... by ShamelessC on Friday April 28, 2023 @01:29PM (#35744427)

> Note that the model is substantially more compute-intensive than Stable Diffusion, so it may be slower even though that space is running on an A100.

Any more specifics on this? Sampling has gotten better too. My primary concern is the amount of memory necessary for a generation (batch size = 1, or I guess "2" using classifier free guidance).

Similar to OpenAI's cascaded diffusion models and GLIDE, you can presumably run the models in sequence, unloading earlier models from memory to make room for the 2nd and 3rd stage models.

Right now, I really only need 256px resolution. So, will I be able to fit the first stage (64px) model in memory on its own with my 12 GB RTX 3060? What about the 2nd stage (64px -> 256px)? 3rd stage?

[ Parent | on HN ]

Re:Stability AI releases DeepFloyd IF, a powerful text-to-im... by dragonwriter on Friday April 28, 2023 @01:32PM (#35744468)

They’ve said the whole pipeline (using the large models in each step with a choice, IIRC) can be run sequenced with 14GB VRAM.

[ Parent | on HN ]